Lune

ICLR2025Top-tier venue

Language Model Alignment in Multilingual Trolley Problems

Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez Adauto, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf

Abstract

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a crosslingual corpus of moral dilemma vignettes in over 100 languages called MUL-TITP. This dataset enables the assessment of LLMs' decision-making processes in diverse linguistic contexts. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions: species, gender, fitness, status, age, and the number of lives involved. By correlating these preferences with the demographic distribution of language speakers and examining the consistency of LLM responses to various prompt paraphrasings, our findings provide insights into cross-lingual and ethical biases of LLMs and their intersection. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems and highlighting the importance of incorporating diverse perspectives in AI ethics. The results underscore the need for further research on the integration of multilingual dimensions in responsible AI research to ensure fair and equitable AI interactions worldwide. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

8 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models cites Aligning AI With Shared Human Values
  • Are aligned neural networks adversarially aligned? cites Language Models are Few-Shot Learners
  • ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs cites Aligning AI With Shared Human Values
  • Aligning AI With Shared Human Values cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers8

  1. LEXam: Benchmarking Legal Reasoning on 340 Law ExamsYu Fan, Jingwei Ni, Jakob Merane, Yang Tian et al.ICLR 2026 · 56 citations
  2. Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment DatasetLily H Zhang, Smitha Milli, Karen Long Jusko, Jonathan Smith et al.ICLR 2026 · 41 citations
  3. ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMsAdi Simhi, Jonathan Herzig, Martin Tutek, Itay Itzhak et al.ICLR 2026 · 3 citations
  4. Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language ModelsChenchen Yuan, Zheyu Zhang, Gjergji KasneciACL 2026
  5. LIVS: A Pluralistic Alignment Dataset for Inclusive Public SpacesRashid Mushkani, Shravan Nayak, Hugo Berard, Allison Cohen et al.ICML 2025

Builds on18

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceWei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos et al.ICML 2024 · 1,212 citations
  3. Refusal in Language Models Is Mediated by a Single DirectionAndy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka et al.NeurIPS 2024 · 1,166 citations
  4. Aligning AI With Shared Human ValuesDan Hendrycks, Collin Burns, Steven Basart, Andrew Critch et al.ICLR 2021 · 878 citations
  5. Are aligned neural networks adversarially aligned?Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski et al.NeurIPS 2023 · 412 citations

Related papers

  1. Multilingual Refusal Alignment for Safer Large Language ModelsAleksandra Krasnodebska, Wojciech Kusa, Aldo LipaniACL Findings 2026
  2. MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech ExplanationJackson Trager, Francielle Vargas, Diego Alves, Matteo Guida et al.EMNLP Findings 2025 · 2 citations
  3. Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?Shaoyang Xu, Weilong Dong, Zishan Guo, Xinwei Wu et al.EMNLP Findings 2024 · 11 citations
  4. The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce HarmAakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant et al.EMNLP 2024 · 3 citations
  5. VITAL: A New Dataset for Benchmarking Pluralistic Alignment in HealthcareAnudeex Shetty, Amin Beheshti, Mark Dras, Usman NaseemACL 2025 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines